pandas 4 处理缺失数据nan

from __future__ import print_function
import pandas as pd
import numpy as np

np.random.seed(1)
dates = pd.date_range('20130101', periods=6)
df = pd.DataFrame(np.arange(24).reshape((6,4)), index=dates, columns=['A', 'B', 'C', 'D'])

df.iloc[0,1] = np.nan
df.iloc[1,2] = np.nan                 # Nan模拟缺失的数据

print(df)
print(df.dropna(axis=0, how='all'))   # how={'any', 'all'}  全部是0才丢掉
print(df.dropna(axis=0, how='any'))   # how={'any', 'all'}  有0就丢掉行
print(df.fillna(value=0))             # 所有的nan用0填充
print(pd.isnull(df))                  # 判断每一个数据是否是Nan,是nan就输出True
print(np.any(df.isnull()) == True)    # 如果有数据缺失，就输出True

以下是所有的输出结果：

print(df)

>              A     B     C   D
> 2013-01-01   0   NaN   2.0   3
> 2013-01-02   4   5.0   NaN   7
> 2013-01-03   8   9.0  10.0  11
> 2013-01-04  12  13.0  14.0  15
> 2013-01-05  16  17.0  18.0  19
> 2013-01-06  20  21.0  22.0  23

print(df.dropna(axis=0, how='all'))   # how={'any', 'all'}

>              A     B     C   D
> 2013-01-01   0   NaN   2.0   3
> 2013-01-02   4   5.0   NaN   7
> 2013-01-03   8   9.0  10.0  11
> 2013-01-04  12  13.0  14.0  15
> 2013-01-05  16  17.0  18.0  19
> 2013-01-06  20  21.0  22.0  23

print(df.dropna(axis=0, how='any'))   # how={'any', 'all'}

>              A     B     C   D
> 2013-01-03   8   9.0  10.0  11
> 2013-01-04  12  13.0  14.0  15
> 2013-01-05  16  17.0  18.0  19
> 2013-01-06  20  21.0  22.0  23

print(df.fillna(value=0))

>              A     B     C   D
> 2013-01-01   0   0.0   2.0   3
> 2013-01-02   4   5.0   0.0   7
> 2013-01-03   8   9.0  10.0  11
> 2013-01-04  12  13.0  14.0  15
> 2013-01-05  16  17.0  18.0  19
> 2013-01-06  20  21.0  22.0  23

print(pd.isnull(df))

>                 A      B      C      D
> 2013-01-01  False   True  False  False
> 2013-01-02  False  False   True  False
> 2013-01-03  False  False  False  False
> 2013-01-04  False  False  False  False
> 2013-01-05  False  False  False  False
> 2013-01-06  False  False  False  False

print(np.any(df.isnull()) == True)

> True

END